org.apache.lucene.analysis.core.TypeTokenFilter Java Examples
The following examples show how to use
org.apache.lucene.analysis.core.TypeTokenFilter.
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: TestConditionalTokenFilter.java From lucene-solr with Apache License 2.0 | 6 votes |
public void testConsistentOffsets() throws IOException { long seed = random().nextLong(); Analyzer analyzer = new Analyzer() { @Override protected TokenStreamComponents createComponents(String fieldName) { Tokenizer source = new NGramTokenizer(); TokenStream sink = new ValidatingTokenFilter(new KeywordRepeatFilter(source), "stage 0"); sink = new ValidatingTokenFilter(sink, "stage 1"); sink = new RandomSkippingFilter(sink, seed, in -> new TypeTokenFilter(in, Collections.singleton("word"))); sink = new ValidatingTokenFilter(sink, "last stage"); return new TokenStreamComponents(source, sink); } }; checkRandomData(random(), analyzer, 1); }
Example #2
Source File: TestConditionalTokenFilter.java From lucene-solr with Apache License 2.0 | 5 votes |
public void testFilteringWithReadahead() throws IOException { CharArraySet protectedTerms = new CharArraySet(2, true); protectedTerms.add("two"); protectedTerms.add("two three"); Analyzer analyzer = new Analyzer() { @Override protected TokenStreamComponents createComponents(String fieldName) { Tokenizer source = new StandardTokenizer(); TokenStream sink = new ShingleFilter(source, 3); sink = new ProtectedTermFilter(protectedTerms, sink, in -> new TypeTokenFilter(in, Collections.singleton("ALL"), true)); return new TokenStreamComponents(source, sink); } }; String input = "one two three four"; try (TokenStream ts = analyzer.tokenStream("", input)) { assertTokenStreamContents(ts, new String[]{ "two", "two three" }, new int[]{ 4, 4 }, new int[]{ 7, 13 }, new int[]{ 2, 0 }, new int[]{ 1, 2 }, 18); } }
Example #3
Source File: KeepTypesFilterFactory.java From Elasticsearch with Apache License 2.0 | 4 votes |
@Override public TokenStream create(TokenStream tokenStream) { return new TypeTokenFilter(tokenStream, keepTypes, true); }
Example #4
Source File: KeepTypesFilterFactory.java From crate with Apache License 2.0 | 4 votes |
@Override public TokenStream create(TokenStream tokenStream) { return new TypeTokenFilter(tokenStream, keepTypes, includeMode == KeepTypesMode.INCLUDE); }